DeepSeek · LLM API pricing

DeepSeek V4 Flash 0731 API pricing: cheapest provider

10 providers sell DeepSeek V4 Flash 0731. DeepInfra is cheapest; the most expensive charges 6.3× as much for the same model.

Cheapest$0.105per 1M · DeepInfra
Input · output$0.08 / $0.18per 1M tokens
Price gap6.3×across 10 providers
Accuracy91.0%GPQA · max reasoning
Context1Mmax tokens

$0.105 DeepInfra6.3× spread$0.66 Microsoft Azure AI Foundry

Compare all 10 providers ⇄ Compare with another model

Already paying for DeepSeek V4 Flash 0731? Check if you overpay →

Standard list prices in USD from each provider's pricing page · last price change Sep 28, 2026 · How we collect and rank prices

Ranked for your volume

DeepSeek V4 Flash 0731 monthly cost by provider

Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.

Input tokens per month (millions)Prompts, context and documents you send.Output tokens per month (millions)Tokens the model generates.

More requirements: caching, context, features, provider

Cached share of input (%)0 = no caching. Only documented cache-read rates qualify.Required context per request (tokens)0 = any. Providers without a sufficient known limit are excluded.Required featureProvider requirement

Provider	Estimated / month	Input / 1M	Output / 1M	Cached input / 1M	Context
1 DeepInfraInference provider - lowest for your volumePricing page	$1.16	$0.08	$0.18	$0.016	1,048,576
2 BasetenInference providerPricing page	$1.82	$0.13	$0.26	$0.028	1,048,576
3 W&B Inference (CoreWeave)Inference providerPricing page	$1.86	$0.13	$0.28	$0.07	262,000
4 Nebius Token FactoryCloud platformPricing page	$1.96	$0.14	$0.28	Not listed	1,024,000
5 SiliconFlowInference providerPricing page	$3.52	$0.22	$0.66	$0.014	1,000,000
6 ScalewayCloud platformBilled in EUR: €0.40 input, €0.80 output per 1M tokens. USD at the ECB rate of Oct 30, 2026 (1.1172).Pricing page	$6.26	$0.4469	$0.8938	$0.0894	256,000
7 Alibaba Cloud Model StudioAI platformSingapore (International) list price; other regions differ.Pricing page	$7.04	$0.44	$1.32	$0.088	1,000,000
8 Cloudflare Workers AICloud platformPricing page	$7.04	$0.44	$1.32	$0.014	1,048,576
9 Microsoft Azure AI FoundryCloud platformPricing page	$7.04	$0.44	$1.32	$0.014	1,000,000
10 Novita AIInference providerPricing page	$7.04	$0.44	$1.32	$0.028	1,048,576

Order depends on listed price for your volume only. No provider pays for its position.

Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.

Share this comparison as a Markdown table

For a post, a doc or a forum answer. The source line links back here, so readers can check today's prices.

Markdown

| DeepSeek V4 Flash 0731 provider | Input / 1M tokens | Output / 1M tokens | 10M in + 2M out per month |
|---|---:|---:|---:|
| DeepInfra | $0.08 | $0.18 | $1.16 |
| Baseten | $0.13 | $0.26 | $1.82 |
| W&B Inference (CoreWeave) | $0.13 | $0.28 | $1.86 |
| Nebius Token Factory | $0.14 | $0.28 | $1.96 |
| SiliconFlow | $0.22 | $0.66 | $3.52 |
| Scaleway | $0.4469 | $0.8938 | $6.26 |
| Alibaba Cloud Model Studio | $0.44 | $1.32 | $7.04 |
| Cloudflare Workers AI | $0.44 | $1.32 | $7.04 |
| Microsoft Azure AI Foundry | $0.44 | $1.32 | $7.04 |
| Novita AI | $0.44 | $1.32 | $7.04 |

Standard list prices as of Oct 31, 2026. Source: [AISelect.online](https://aiselect.online/models/deepseek-v4-flash-0731)

Accuracy: GPQA Diamond (graduate-level science questions) measured by Epoch AI (CC BY 4.0) on deepseek-v4-flash-0731_max, run Aug 2, 2026. The model is the same at every provider, though quantized deployments can score lower.

Price history

The cheapest price has not changed since tracking started on Sep 28, 2026: $0.105 per 1M tokens at DeepInfra. All price changes

Switch to the cheapest provider

Switch to DeepInfra

Already using the OpenAI SDK? Change the base URL, key and model name:

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.deepinfra.com/v1/openai",
    api_key=os.environ["DEEPINFRA_API_KEY"],
)
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Flash-0731",
    messages=[{"role": "user", "content": "Hello"}],
)

Base URL from DeepInfra's API docs, model name from the open pricing datasets. Check the model page in DeepInfra's docs before you switch production traffic.

Compare DeepSeek V4 Flash 0731 with another model

DeepSeek V4 Flash 0731 vs GPT-6 Luna DeepSeek V4 Flash 0731 vs gpt-oss-120b DeepSeek V4 Flash 0731 vs DeepSeek V4 Pro

Or pick any model

Model A

Model B

Before you pick a provider

Context windows differ by provider, from 256K to 1M tokens. A cheaper host may not accept your longest prompts.

9 of 10 providers list a cached-input price. Repeated system prompts or documents can cost much less there than the standard input rate shown above.

Keep comparing

More DeepSeek models

DeepSeek V4 Pro 0813, DeepSeek-R1, DeepSeek-V3, DeepSeek-V3.2, DeepSeek-V4.1-Flash, DeepSeek-V3.1, DeepSeek-V4-Flash, DeepSeek V4 Pro

All DeepSeek API prices - All LLM API prices - Watch DeepSeek V4 Flash 0731 prices (RSS) - Methodology